PETALS: Improving Learning of Expert Skill in Humanitarian Demining - - PowerPoint PPT Presentation

▶
petals improving learning of expert skill in humanitarian
SMART_READER_LITE
LIVE PREVIEW

PETALS: Improving Learning of Expert Skill in Humanitarian Demining - - PowerPoint PPT Presentation

Nov 04, 2023 267 likes •806 views

PETALS: Improving Learning of Expert Skill in Humanitarian Demining Lahiru Jayatilaka (Red Lotus Technologies) David M. Sengeh (IBM Research - Africa) Charles Herrmann (Cornell University) Luca Bertuccelli (Sensitech) Dimitrios Antos (Verily Life

slide-1
SLIDE 1

PETALS: Improving Learning of Expert Skill in Humanitarian Demining

Lahiru Jayatilaka (Red Lotus Technologies) David M. Sengeh (IBM Research - Africa) Charles Herrmann (Cornell University) Luca Bertuccelli (Sensitech) Dimitrios Antos (Verily Life Sciences) Barbara J. Grosz (Harvard School of Engineering and Applied Sciences) Krzysztof Z. Gajos (Harvard School of Engineering and Applied Sciences) .org

slide-2
SLIDE 2

Photo: Justin Ide/Harvard Staff Photographer

Jayatilaka Lahiru

slide-3
SLIDE 3

war between Tamil Tigers 1983–2009 and Sri Lankan army

slide-4
SLIDE 4

Photo: Devaka Seneviratne

war between Tamil Tigers and Sri Lankan army 1983–2009

slide-5
SLIDE 5
slide-6
SLIDE 6

in 61 countries 6,461 casualties in 2015 78% were civilians 38% were children

Source: Landmine Monitor 2016

slide-7
SLIDE 7

Photo: Adam Jones

slide-8
SLIDE 8

Photo: HALO Trust Archives

slide-9
SLIDE 9

Lahiru’s Mission:

Use the power of Computer Science to improve the safety and efficiency of humanitarian landmine clearance

slide-10
SLIDE 10

Landmine Clearance Basics

Photo: Halo Trust Archives

  • Landmine detection still

performed primarily with handheld metal detectors

slide-11
SLIDE 11

Landmine Clearance Basics

  • Landmine detection still

performed primarily with handheld metal detectors

  • For every landmine, 100 pieces
  • f metallic debris are found
slide-12
SLIDE 12

Landmine Clearance Basics

  • Landmine detection still

performed primarily with handheld metal detectors

  • For every landmine, 100 pieces
  • f metallic debris are found
  • When mines are placed in a

cluster configuration, it is hard to tell how many mines there are and where they are located

slide-13
SLIDE 13

Landmine Clearance Basics

  • Landmine detection still

performed primarily with handheld metal detectors

  • For every landmine, 100 pieces
  • f metallic debris are found
  • When mines are placed in a

cluster configuration, it is hard to tell how many mines there are and where they are located

slide-14
SLIDE 14

Expert Approach: Metallic Signature Method

  • Landmine detection still

performed primarily with handheld metal detectors

  • For every landmine, 100 pieces
  • f metallic debris are found
  • When mines are placed in a

cluster configuration, it is hard to tell how many mines there are and where they are located

  • Experts have a way of dealing

with clutter and cluster configurations, but their method is hard to teach

slide-15
SLIDE 15

x x x x

x

  • Landmine detection still

performed primarily with handheld metal detectors

  • For every landmine, 100 pieces
  • f metallic debris are found
  • When mines are placed in a

cluster configuration, it is hard to tell how many mines there are and where they are located

  • Experts have a way of dealing

with clutter and cluster configurations, but their method is hard to teach

Expert Approach: Metallic Signature Method

slide-16
SLIDE 16

Key Idea: Visualize Metallic Signatures

x x x x x x x x x x

slide-17
SLIDE 17

Key Idea: Visualize Metallic Signatures

x x x x x x x x x x

slide-18
SLIDE 18

Approach 0: Support Deminer in the Field

slide-19
SLIDE 19

Approach 0: Support Deminer in the Field

Camera Display Trigger Color patch

slide-20
SLIDE 20

Approach 0: It Works! But…

[Lahiru G. Jayatilaka, Luca F. Bertuccelli, James Staszewski, and Krzysztof Z. Gajos. Evaluating a pattern-based visual support approach for humanitarian landmine clearance. In Proc. CHI '11, New York, NY, USA, 2011. ACM.]

slide-21
SLIDE 21

Approach 1: Scaffold Trainees’ Learning

slide-22
SLIDE 22

Approach 1: Scaffold Trainees’ Learning

slide-23
SLIDE 23

Approach 1: Scaffold Trainees’ Learning

slide-24
SLIDE 24

Approach 1: Scaffold Trainees’ Learning

Instructor console Overhead camera tracking computer training lane

slide-25
SLIDE 25

Camera Trigger Color patch

Approach 1: Scaffold Trainees’ Learning

slide-26
SLIDE 26

Approach 1: Support Trainees

Approach 1: Scaffold Trainees’ Learning

Display

slide-27
SLIDE 27

Approach 1: Support Trainees

Approach 1: Scaffold Trainees’ Learning

slide-28
SLIDE 28

Approach 1: Support Trainees

Approach 1: Scaffold Trainees’ Learning

slide-29
SLIDE 29

Approach 1: Lessons Learned

  • Real-time visualizations were not

effective

  • PETALS allowed instructors to

monitor performance of multiple trainees simultaneously

  • PETALS allowed instructors to

communicate personalized process feedback after completion of each practice lane

slide-30
SLIDE 30

Approach 2: Support Instructors

slide-31
SLIDE 31

Approach 2: Support Instructors

slide-32
SLIDE 32

Gapping Target Lock

Approach 2: Support Instructors

slide-33
SLIDE 33

Approach 2: Support Instructors

slide-34
SLIDE 34

Approach 2: Support Instructors

Instructor console Overhead camera tracking computer training lane

slide-35
SLIDE 35

Approach 2: Support Instructors

Instructor console Overhead camera tracking computer training lane

“I can walk up here [to the instructor console] and within 2 seconds I can say, ‘he doesn’t need anymore help’, ‘he doesn’t need anymore help’ ... or ‘this guy might need help’.”

–an HDTC instructor

slide-36
SLIDE 36

Approach 2: Support Instructors

slide-37
SLIDE 37

Summative Evaluation

slide-38
SLIDE 38

Summative Evaluation

slide-39
SLIDE 39

Summative Evaluation

  • 1. Initial lecture
slide-40
SLIDE 40

Summative Evaluation

  • 2. Training
slide-41
SLIDE 41

Summative Evaluation

  • 3. Exam
slide-42
SLIDE 42
  • 1. Initial lecture
slide-43
SLIDE 43

–Johnny Appleseed

“Type a quote here.”

  • 2. Training
slide-44
SLIDE 44
  • 2. Training
slide-45
SLIDE 45
  • 2. Training
slide-46
SLIDE 46
  • 3. Exam
slide-47
SLIDE 47

Take Aways

  • Metal detectors are still the

primary tool in humanitarian landmine clearance

slide-48
SLIDE 48

Take Aways

  • The Metallic Signature technique

is used by experts to reason about type of buried objects and cluster

  • configurations. But this technique

is hard to learn.

  • Metal detectors are still the

primary tool in humanitarian landmine clearance

x x x x x x x x x x

slide-49
SLIDE 49

Take Aways

  • Real time visualization of metallic

signatures increased cognitive burden on trainees instead of reducing it.

  • Metal detectors are still the

primary tool in humanitarian landmine clearance

  • The Metallic Signature technique

is used by experts to reason about type of buried objects and cluster

  • configurations. But this technique

is hard to learn.

slide-50
SLIDE 50

Take Aways

  • Visualization helped trainers

provide trainees with immediate and personalized process feedback.

  • Metal detectors are still the

primary tool in humanitarian landmine clearance

  • The Metallic Signature technique

is used by experts to reason about type of buried objects and cluster

  • configurations. But this technique

is hard to learn.

  • Real time visualization of metallic

signatures increased cognitive burden on trainees instead of reducing it.

slide-51
SLIDE 51

Take Aways

  • Visualization helped trainers

provide trainees with immediate and personalized process feedback.

  • Metal detectors are still the

primary tool in humanitarian landmine clearance

  • The Metallic Signature technique

is used by experts to reason about type of buried objects and cluster

  • configurations. But this technique

is hard to learn.

  • Real time visualization of metallic

signatures increased cognitive burden on trainees instead of reducing it.

.org

Lahiru Jayatilaka 


(Red Lotus Technologies)

David M. Sengeh 


(IBM Research - Africa)

Charles Herrmann 


(Cornell University)

Luca Bertuccelli 


(Sensitech)

Dimitrios Antos 


(Verily Life Sciences)

Barbara J. Grosz 


(Harvard School of Engineering and Applied Sciences)

Krzysztof Z. Gajos 


(Harvard School of Engineering and Applied Sciences)

slide-52
SLIDE 52

Innovation = Invention + Implementation